Fair Meta-Learning: Learning How to Learn Fairly
원문 초록
Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-learning approaches in such situations. For models that can be trained through gradient descent, we demonstrate that there are some parameter configurations that allow models to be optimized from a few number of gradient steps and with minimal data which are both fair and accurate. To learn such weight sets, we adapt the popular MAML algorithm to Fair-MAML by the inclusion of a fairness regularization term. In practice, Fair-MAML allows practitioners to train fair machine learning models from only a few examples when data from related tasks is available. We empirically exhibit the value of this technique by comparing to relevant baselines.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Robustly Improving LLM Fairness in Realistic Settings via Interpretability
Improving Fairness of Large Language Models in Multi-document Summarization
Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
IndianBailJudgments-1200: A Multi-Attribute Dataset for Legal NLP on Indian Bail Orders
FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation
Fair for a few: Improving Fairness in Doubly Imbalanced Datasets
토론
이 논문과 연결된 포럼 글이 아직 없습니다.